Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 36501
    Prev
    Next
    INDEX
    Explanations

    references to populations and demographic data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.84
    дравству
    -0.53
     Fácil
    -0.46
    thx
    -0.45
    easy
    -0.44
    Step
    -0.43
     Mudah
    -0.43
    consejos
    -0.43
     dritte
    -0.43
    znál
    -0.43
    POSITIVE LOGITS
     population
    1.13
     Population
    1.07
    population
    1.01
    Population
    0.98
     populations
    0.98
     POPULATION
    0.89
     Populations
    0.86
     populace
    0.75
     popolazione
    0.74
     população
    0.73
    Activations Density 0.024%

    No Known Activations